1. Patchew
  2. linux
  3. [PATCH v6 0/9] fs: multigrain timestamp redux
  4. View patch

[PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events

Jeff Layton posted 9 patches 1 year, 6 months ago
There is a newer version of this series
[PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events
Posted by Jeff Layton 1 year, 6 months ago 
Four percpu counters for counting various stats around mgtimes, and a
new debugfs file for displaying them:

- number of attempted ctime updates
- number of successful i_ctime_nsec swaps
- number of fine-grained timestamp fetches
- number of floor value swaps

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/inode.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 69 insertions(+), 1 deletion(-)

diff --git a/fs/inode.c b/fs/inode.c
index 869994285e87..fff844345c35 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -21,6 +21,8 @@
 #include <linux/list_lru.h>
 #include <linux/iversion.h>
 #include <linux/rw_hint.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
 #include <trace/events/writeback.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/timestamp.h>
@@ -80,6 +82,10 @@ EXPORT_SYMBOL(empty_aops);
 
 static DEFINE_PER_CPU(unsigned long, nr_inodes);
 static DEFINE_PER_CPU(unsigned long, nr_unused);
+static DEFINE_PER_CPU(unsigned long, mg_ctime_updates);
+static DEFINE_PER_CPU(unsigned long, mg_fine_stamps);
+static DEFINE_PER_CPU(unsigned long, mg_floor_swaps);
+static DEFINE_PER_CPU(unsigned long, mg_ctime_swaps);
 
 static struct kmem_cache *inode_cachep __ro_after_init;
 
@@ -101,6 +107,42 @@ static inline long get_nr_inodes_unused(void)
 	return sum < 0 ? 0 : sum;
 }
 
+static long get_mg_ctime_updates(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_ctime_updates, i);
+	return sum < 0 ? 0 : sum;
+}
+
+static long get_mg_fine_stamps(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_fine_stamps, i);
+	return sum < 0 ? 0 : sum;
+}
+
+static long get_mg_floor_swaps(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_floor_swaps, i);
+	return sum < 0 ? 0 : sum;
+}
+
+static long get_mg_ctime_swaps(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_ctime_swaps, i);
+	return sum < 0 ? 0 : sum;
+}
+
 long get_nr_dirty_inodes(void)
 {
 	/* not actually dirty inodes, but a wild approximation */
@@ -2655,6 +2697,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 
 			/* Get a fine-grained time */
 			fine = ktime_get();
+			this_cpu_inc(mg_fine_stamps);
 
 			/*
 			 * If the cmpxchg works, we take the new floor value. If
@@ -2663,11 +2706,14 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 			 * as good, so keep it.
 			 */
 			old = floor;
-			if (!atomic64_try_cmpxchg(&ctime_floor, &old, fine))
+			if (atomic64_try_cmpxchg(&ctime_floor, &old, fine))
+				this_cpu_inc(mg_floor_swaps);
+			else
 				fine = old;
 			now = ktime_mono_to_real(fine);
 		}
 	}
+	this_cpu_inc(mg_ctime_updates);
 	now_ts = timestamp_truncate(ktime_to_timespec64(now), inode);
 	cur = cns;
 
@@ -2682,6 +2728,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 		/* If swap occurred, then we're (mostly) done */
 		inode->i_ctime_sec = now_ts.tv_sec;
 		trace_ctime_ns_xchg(inode, cns, now_ts.tv_nsec, cur);
+		this_cpu_inc(mg_ctime_swaps);
 	} else {
 		/*
 		 * Was the change due to someone marking the old ctime QUERIED?
@@ -2751,3 +2798,24 @@ umode_t mode_strip_sgid(struct mnt_idmap *idmap,
 	return mode & ~S_ISGID;
 }
 EXPORT_SYMBOL(mode_strip_sgid);
+
+static int mgts_show(struct seq_file *s, void *p)
+{
+	long ctime_updates = get_mg_ctime_updates();
+	long ctime_swaps = get_mg_ctime_swaps();
+	long fine_stamps = get_mg_fine_stamps();
+	long floor_swaps = get_mg_floor_swaps();
+
+	seq_printf(s, "%lu %lu %lu %lu\n",
+		   ctime_updates, ctime_swaps, fine_stamps, floor_swaps);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mgts);
+
+static int __init mg_debugfs_init(void)
+{
+	debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
+	return 0;
+}
+late_initcall(mg_debugfs_init);

-- 
2.45.2
Re: [PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events
Posted by Darrick J. Wong 1 year, 6 months ago 
On Mon, Jul 15, 2024 at 08:48:54AM -0400, Jeff Layton wrote:
> Four percpu counters for counting various stats around mgtimes, and a
> new debugfs file for displaying them:
> 
> - number of attempted ctime updates
> - number of successful i_ctime_nsec swaps
> - number of fine-grained timestamp fetches
> - number of floor value swaps
> 
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Signed-off-by: Jeff Layton <jlayton@kernel.org>
> ---
>  fs/inode.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 69 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/inode.c b/fs/inode.c
> index 869994285e87..fff844345c35 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -21,6 +21,8 @@
>  #include <linux/list_lru.h>
>  #include <linux/iversion.h>
>  #include <linux/rw_hint.h>
> +#include <linux/seq_file.h>
> +#include <linux/debugfs.h>
>  #include <trace/events/writeback.h>
>  #define CREATE_TRACE_POINTS
>  #include <trace/events/timestamp.h>
> @@ -80,6 +82,10 @@ EXPORT_SYMBOL(empty_aops);
>  
>  static DEFINE_PER_CPU(unsigned long, nr_inodes);
>  static DEFINE_PER_CPU(unsigned long, nr_unused);
> +static DEFINE_PER_CPU(unsigned long, mg_ctime_updates);
> +static DEFINE_PER_CPU(unsigned long, mg_fine_stamps);
> +static DEFINE_PER_CPU(unsigned long, mg_floor_swaps);
> +static DEFINE_PER_CPU(unsigned long, mg_ctime_swaps);

Should this all get switched off if CONFIG_DEBUG_FS=n?

--D

>  
>  static struct kmem_cache *inode_cachep __ro_after_init;
>  
> @@ -101,6 +107,42 @@ static inline long get_nr_inodes_unused(void)
>  	return sum < 0 ? 0 : sum;
>  }
>  
> +static long get_mg_ctime_updates(void)
> +{
> +	int i;
> +	long sum = 0;
> +	for_each_possible_cpu(i)
> +		sum += per_cpu(mg_ctime_updates, i);
> +	return sum < 0 ? 0 : sum;
> +}
> +
> +static long get_mg_fine_stamps(void)
> +{
> +	int i;
> +	long sum = 0;
> +	for_each_possible_cpu(i)
> +		sum += per_cpu(mg_fine_stamps, i);
> +	return sum < 0 ? 0 : sum;
> +}
> +
> +static long get_mg_floor_swaps(void)
> +{
> +	int i;
> +	long sum = 0;
> +	for_each_possible_cpu(i)
> +		sum += per_cpu(mg_floor_swaps, i);
> +	return sum < 0 ? 0 : sum;
> +}
> +
> +static long get_mg_ctime_swaps(void)
> +{
> +	int i;
> +	long sum = 0;
> +	for_each_possible_cpu(i)
> +		sum += per_cpu(mg_ctime_swaps, i);
> +	return sum < 0 ? 0 : sum;
> +}
> +
>  long get_nr_dirty_inodes(void)
>  {
>  	/* not actually dirty inodes, but a wild approximation */
> @@ -2655,6 +2697,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
>  
>  			/* Get a fine-grained time */
>  			fine = ktime_get();
> +			this_cpu_inc(mg_fine_stamps);
>  
>  			/*
>  			 * If the cmpxchg works, we take the new floor value. If
> @@ -2663,11 +2706,14 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
>  			 * as good, so keep it.
>  			 */
>  			old = floor;
> -			if (!atomic64_try_cmpxchg(&ctime_floor, &old, fine))
> +			if (atomic64_try_cmpxchg(&ctime_floor, &old, fine))
> +				this_cpu_inc(mg_floor_swaps);
> +			else
>  				fine = old;
>  			now = ktime_mono_to_real(fine);
>  		}
>  	}
> +	this_cpu_inc(mg_ctime_updates);
>  	now_ts = timestamp_truncate(ktime_to_timespec64(now), inode);
>  	cur = cns;
>  
> @@ -2682,6 +2728,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
>  		/* If swap occurred, then we're (mostly) done */
>  		inode->i_ctime_sec = now_ts.tv_sec;
>  		trace_ctime_ns_xchg(inode, cns, now_ts.tv_nsec, cur);
> +		this_cpu_inc(mg_ctime_swaps);
>  	} else {
>  		/*
>  		 * Was the change due to someone marking the old ctime QUERIED?
> @@ -2751,3 +2798,24 @@ umode_t mode_strip_sgid(struct mnt_idmap *idmap,
>  	return mode & ~S_ISGID;
>  }
>  EXPORT_SYMBOL(mode_strip_sgid);
> +
> +static int mgts_show(struct seq_file *s, void *p)
> +{
> +	long ctime_updates = get_mg_ctime_updates();
> +	long ctime_swaps = get_mg_ctime_swaps();
> +	long fine_stamps = get_mg_fine_stamps();
> +	long floor_swaps = get_mg_floor_swaps();
> +
> +	seq_printf(s, "%lu %lu %lu %lu\n",
> +		   ctime_updates, ctime_swaps, fine_stamps, floor_swaps);
> +	return 0;
> +}
> +
> +DEFINE_SHOW_ATTRIBUTE(mgts);
> +
> +static int __init mg_debugfs_init(void)
> +{
> +	debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
> +	return 0;
> +}
> +late_initcall(mg_debugfs_init);
> 
> -- 
> 2.45.2
> 
>
Re: [PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events
Posted by Jeff Layton 1 year, 6 months ago 
On Mon, 2024-07-15 at 11:32 -0700, Darrick J. Wong wrote:
> On Mon, Jul 15, 2024 at 08:48:54AM -0400, Jeff Layton wrote:
> > Four percpu counters for counting various stats around mgtimes, and
> > a
> > new debugfs file for displaying them:
> > 
> > - number of attempted ctime updates
> > - number of successful i_ctime_nsec swaps
> > - number of fine-grained timestamp fetches
> > - number of floor value swaps
> > 
> > Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> > Signed-off-by: Jeff Layton <jlayton@kernel.org>
> > ---
> >  fs/inode.c | 70
> > +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> >  1 file changed, 69 insertions(+), 1 deletion(-)
> > 
> > diff --git a/fs/inode.c b/fs/inode.c
> > index 869994285e87..fff844345c35 100644
> > --- a/fs/inode.c
> > +++ b/fs/inode.c
> > @@ -21,6 +21,8 @@
> >  #include <linux/list_lru.h>
> >  #include <linux/iversion.h>
> >  #include <linux/rw_hint.h>
> > +#include <linux/seq_file.h>
> > +#include <linux/debugfs.h>
> >  #include <trace/events/writeback.h>
> >  #define CREATE_TRACE_POINTS
> >  #include <trace/events/timestamp.h>
> > @@ -80,6 +82,10 @@ EXPORT_SYMBOL(empty_aops);
> >  
> >  static DEFINE_PER_CPU(unsigned long, nr_inodes);
> >  static DEFINE_PER_CPU(unsigned long, nr_unused);
> > +static DEFINE_PER_CPU(unsigned long, mg_ctime_updates);
> > +static DEFINE_PER_CPU(unsigned long, mg_fine_stamps);
> > +static DEFINE_PER_CPU(unsigned long, mg_floor_swaps);
> > +static DEFINE_PER_CPU(unsigned long, mg_ctime_swaps);
> 
> Should this all get switched off if CONFIG_DEBUG_FS=n?
> 
> --D
> 

Sure, why not. That's simple enough to do.

I pushed an updated mgtime branch to my git tree. Here's the updated
patch that's the only difference:

    https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/commit/?h=mgtime&id=ee7fe6e9c0598754861c8620230f15f3de538ca5

Seems to build OK both with and without CONFIG_DEBUG_FS.
 
> >  
> >  static struct kmem_cache *inode_cachep __ro_after_init;
> >  
> > @@ -101,6 +107,42 @@ static inline long get_nr_inodes_unused(void)
> >  	return sum < 0 ? 0 : sum;
> >  }
> >  
> > +static long get_mg_ctime_updates(void)
> > +{
> > +	int i;
> > +	long sum = 0;
> > +	for_each_possible_cpu(i)
> > +		sum += per_cpu(mg_ctime_updates, i);
> > +	return sum < 0 ? 0 : sum;
> > +}
> > +
> > +static long get_mg_fine_stamps(void)
> > +{
> > +	int i;
> > +	long sum = 0;
> > +	for_each_possible_cpu(i)
> > +		sum += per_cpu(mg_fine_stamps, i);
> > +	return sum < 0 ? 0 : sum;
> > +}
> > +
> > +static long get_mg_floor_swaps(void)
> > +{
> > +	int i;
> > +	long sum = 0;
> > +	for_each_possible_cpu(i)
> > +		sum += per_cpu(mg_floor_swaps, i);
> > +	return sum < 0 ? 0 : sum;
> > +}
> > +
> > +static long get_mg_ctime_swaps(void)
> > +{
> > +	int i;
> > +	long sum = 0;
> > +	for_each_possible_cpu(i)
> > +		sum += per_cpu(mg_ctime_swaps, i);
> > +	return sum < 0 ? 0 : sum;
> > +}
> > +
> >  long get_nr_dirty_inodes(void)
> >  {
> >  	/* not actually dirty inodes, but a wild approximation */
> > @@ -2655,6 +2697,7 @@ struct timespec64
> > inode_set_ctime_current(struct inode *inode)
> >  
> >  			/* Get a fine-grained time */
> >  			fine = ktime_get();
> > +			this_cpu_inc(mg_fine_stamps);
> >  
> >  			/*
> >  			 * If the cmpxchg works, we take the new
> > floor value. If
> > @@ -2663,11 +2706,14 @@ struct timespec64
> > inode_set_ctime_current(struct inode *inode)
> >  			 * as good, so keep it.
> >  			 */
> >  			old = floor;
> > -			if (!atomic64_try_cmpxchg(&ctime_floor,
> > &old, fine))
> > +			if (atomic64_try_cmpxchg(&ctime_floor,
> > &old, fine))
> > +				this_cpu_inc(mg_floor_swaps);
> > +			else
> >  				fine = old;
> >  			now = ktime_mono_to_real(fine);
> >  		}
> >  	}
> > +	this_cpu_inc(mg_ctime_updates);
> >  	now_ts = timestamp_truncate(ktime_to_timespec64(now),
> > inode);
> >  	cur = cns;
> >  
> > @@ -2682,6 +2728,7 @@ struct timespec64
> > inode_set_ctime_current(struct inode *inode)
> >  		/* If swap occurred, then we're (mostly) done */
> >  		inode->i_ctime_sec = now_ts.tv_sec;
> >  		trace_ctime_ns_xchg(inode, cns, now_ts.tv_nsec,
> > cur);
> > +		this_cpu_inc(mg_ctime_swaps);
> >  	} else {
> >  		/*
> >  		 * Was the change due to someone marking the old
> > ctime QUERIED?
> > @@ -2751,3 +2798,24 @@ umode_t mode_strip_sgid(struct mnt_idmap
> > *idmap,
> >  	return mode & ~S_ISGID;
> >  }
> >  EXPORT_SYMBOL(mode_strip_sgid);
> > +
> > +static int mgts_show(struct seq_file *s, void *p)
> > +{
> > +	long ctime_updates = get_mg_ctime_updates();
> > +	long ctime_swaps = get_mg_ctime_swaps();
> > +	long fine_stamps = get_mg_fine_stamps();
> > +	long floor_swaps = get_mg_floor_swaps();
> > +
> > +	seq_printf(s, "%lu %lu %lu %lu\n",
> > +		   ctime_updates, ctime_swaps, fine_stamps,
> > floor_swaps);
> > +	return 0;
> > +}
> > +
> > +DEFINE_SHOW_ATTRIBUTE(mgts);
> > +
> > +static int __init mg_debugfs_init(void)
> > +{
> > +	debugfs_create_file("multigrain_timestamps", S_IFREG |
> > S_IRUGO, NULL, NULL, &mgts_fops);
> > +	return 0;
> > +}
> > +late_initcall(mg_debugfs_init);
> > 
> > -- 
> > 2.45.2
> > 
> > 

-- 
Jeff Layton <jlayton@kernel.org>
Re: [PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events
Posted by Jan Kara 1 year, 6 months ago 
On Mon 15-07-24 15:53:42, Jeff Layton wrote:
> On Mon, 2024-07-15 at 11:32 -0700, Darrick J. Wong wrote:
> > On Mon, Jul 15, 2024 at 08:48:54AM -0400, Jeff Layton wrote:
> > > Four percpu counters for counting various stats around mgtimes, and
> > > a
> > > new debugfs file for displaying them:
> > > 
> > > - number of attempted ctime updates
> > > - number of successful i_ctime_nsec swaps
> > > - number of fine-grained timestamp fetches
> > > - number of floor value swaps
> > > 
> > > Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> > > Signed-off-by: Jeff Layton <jlayton@kernel.org>
> > > ---
> > >  fs/inode.c | 70
> > > +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> > >  1 file changed, 69 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/fs/inode.c b/fs/inode.c
> > > index 869994285e87..fff844345c35 100644
> > > --- a/fs/inode.c
> > > +++ b/fs/inode.c
> > > @@ -21,6 +21,8 @@
> > >  #include <linux/list_lru.h>
> > >  #include <linux/iversion.h>
> > >  #include <linux/rw_hint.h>
> > > +#include <linux/seq_file.h>
> > > +#include <linux/debugfs.h>
> > >  #include <trace/events/writeback.h>
> > >  #define CREATE_TRACE_POINTS
> > >  #include <trace/events/timestamp.h>
> > > @@ -80,6 +82,10 @@ EXPORT_SYMBOL(empty_aops);
> > >  
> > >  static DEFINE_PER_CPU(unsigned long, nr_inodes);
> > >  static DEFINE_PER_CPU(unsigned long, nr_unused);
> > > +static DEFINE_PER_CPU(unsigned long, mg_ctime_updates);
> > > +static DEFINE_PER_CPU(unsigned long, mg_fine_stamps);
> > > +static DEFINE_PER_CPU(unsigned long, mg_floor_swaps);
> > > +static DEFINE_PER_CPU(unsigned long, mg_ctime_swaps);
> > 
> > Should this all get switched off if CONFIG_DEBUG_FS=n?
> > 
> > --D
> > 
> 
> Sure, why not. That's simple enough to do.
> 
> I pushed an updated mgtime branch to my git tree. Here's the updated
> patch that's the only difference:
> 
>     https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/commit/?h=mgtime&id=ee7fe6e9c0598754861c8620230f15f3de538ca5
> 
> Seems to build OK both with and without CONFIG_DEBUG_FS.

Looks good to me. Feel free to add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

>  
> > >  
> > >  static struct kmem_cache *inode_cachep __ro_after_init;
> > >  
> > > @@ -101,6 +107,42 @@ static inline long get_nr_inodes_unused(void)
> > >  	return sum < 0 ? 0 : sum;
> > >  }
> > >  
> > > +static long get_mg_ctime_updates(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_ctime_updates, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_fine_stamps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_fine_stamps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_floor_swaps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_floor_swaps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_ctime_swaps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_ctime_swaps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > >  long get_nr_dirty_inodes(void)
> > >  {
> > >  	/* not actually dirty inodes, but a wild approximation */
> > > @@ -2655,6 +2697,7 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  
> > >  			/* Get a fine-grained time */
> > >  			fine = ktime_get();
> > > +			this_cpu_inc(mg_fine_stamps);
> > >  
> > >  			/*
> > >  			 * If the cmpxchg works, we take the new
> > > floor value. If
> > > @@ -2663,11 +2706,14 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  			 * as good, so keep it.
> > >  			 */
> > >  			old = floor;
> > > -			if (!atomic64_try_cmpxchg(&ctime_floor,
> > > &old, fine))
> > > +			if (atomic64_try_cmpxchg(&ctime_floor,
> > > &old, fine))
> > > +				this_cpu_inc(mg_floor_swaps);
> > > +			else
> > >  				fine = old;
> > >  			now = ktime_mono_to_real(fine);
> > >  		}
> > >  	}
> > > +	this_cpu_inc(mg_ctime_updates);
> > >  	now_ts = timestamp_truncate(ktime_to_timespec64(now),
> > > inode);
> > >  	cur = cns;
> > >  
> > > @@ -2682,6 +2728,7 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  		/* If swap occurred, then we're (mostly) done */
> > >  		inode->i_ctime_sec = now_ts.tv_sec;
> > >  		trace_ctime_ns_xchg(inode, cns, now_ts.tv_nsec,
> > > cur);
> > > +		this_cpu_inc(mg_ctime_swaps);
> > >  	} else {
> > >  		/*
> > >  		 * Was the change due to someone marking the old
> > > ctime QUERIED?
> > > @@ -2751,3 +2798,24 @@ umode_t mode_strip_sgid(struct mnt_idmap
> > > *idmap,
> > >  	return mode & ~S_ISGID;
> > >  }
> > >  EXPORT_SYMBOL(mode_strip_sgid);
> > > +
> > > +static int mgts_show(struct seq_file *s, void *p)
> > > +{
> > > +	long ctime_updates = get_mg_ctime_updates();
> > > +	long ctime_swaps = get_mg_ctime_swaps();
> > > +	long fine_stamps = get_mg_fine_stamps();
> > > +	long floor_swaps = get_mg_floor_swaps();
> > > +
> > > +	seq_printf(s, "%lu %lu %lu %lu\n",
> > > +		   ctime_updates, ctime_swaps, fine_stamps,
> > > floor_swaps);
> > > +	return 0;
> > > +}
> > > +
> > > +DEFINE_SHOW_ATTRIBUTE(mgts);
> > > +
> > > +static int __init mg_debugfs_init(void)
> > > +{
> > > +	debugfs_create_file("multigrain_timestamps", S_IFREG |
> > > S_IRUGO, NULL, NULL, &mgts_fops);
> > > +	return 0;
> > > +}
> > > +late_initcall(mg_debugfs_init);
> > > 
> > > -- 
> > > 2.45.2
> > > 
> > > 
> 
> -- 
> Jeff Layton <jlayton@kernel.org>
> 
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR
Re: [PATCH v6 3/9] fs: add percpu counters for significant multigrain timestamp events
Posted by Darrick J. Wong 1 year, 6 months ago 
On Mon, Jul 15, 2024 at 03:53:42PM -0400, Jeff Layton wrote:
> On Mon, 2024-07-15 at 11:32 -0700, Darrick J. Wong wrote:
> > On Mon, Jul 15, 2024 at 08:48:54AM -0400, Jeff Layton wrote:
> > > Four percpu counters for counting various stats around mgtimes, and
> > > a
> > > new debugfs file for displaying them:
> > > 
> > > - number of attempted ctime updates
> > > - number of successful i_ctime_nsec swaps
> > > - number of fine-grained timestamp fetches
> > > - number of floor value swaps
> > > 
> > > Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> > > Signed-off-by: Jeff Layton <jlayton@kernel.org>
> > > ---
> > >  fs/inode.c | 70
> > > +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> > >  1 file changed, 69 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/fs/inode.c b/fs/inode.c
> > > index 869994285e87..fff844345c35 100644
> > > --- a/fs/inode.c
> > > +++ b/fs/inode.c
> > > @@ -21,6 +21,8 @@
> > >  #include <linux/list_lru.h>
> > >  #include <linux/iversion.h>
> > >  #include <linux/rw_hint.h>
> > > +#include <linux/seq_file.h>
> > > +#include <linux/debugfs.h>
> > >  #include <trace/events/writeback.h>
> > >  #define CREATE_TRACE_POINTS
> > >  #include <trace/events/timestamp.h>
> > > @@ -80,6 +82,10 @@ EXPORT_SYMBOL(empty_aops);
> > >  
> > >  static DEFINE_PER_CPU(unsigned long, nr_inodes);
> > >  static DEFINE_PER_CPU(unsigned long, nr_unused);
> > > +static DEFINE_PER_CPU(unsigned long, mg_ctime_updates);
> > > +static DEFINE_PER_CPU(unsigned long, mg_fine_stamps);
> > > +static DEFINE_PER_CPU(unsigned long, mg_floor_swaps);
> > > +static DEFINE_PER_CPU(unsigned long, mg_ctime_swaps);
> > 
> > Should this all get switched off if CONFIG_DEBUG_FS=n?
> > 
> > --D
> > 
> 
> Sure, why not. That's simple enough to do.
> 
> I pushed an updated mgtime branch to my git tree. Here's the updated
> patch that's the only difference:
> 
>     https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/commit/?h=mgtime&id=ee7fe6e9c0598754861c8620230f15f3de538ca5
> 
> Seems to build OK both with and without CONFIG_DEBUG_FS.

LGTM,
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

Thank you for your work on all this multigrain stuff. :)

--D

>  
> > >  
> > >  static struct kmem_cache *inode_cachep __ro_after_init;
> > >  
> > > @@ -101,6 +107,42 @@ static inline long get_nr_inodes_unused(void)
> > >  	return sum < 0 ? 0 : sum;
> > >  }
> > >  
> > > +static long get_mg_ctime_updates(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_ctime_updates, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_fine_stamps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_fine_stamps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_floor_swaps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_floor_swaps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > > +static long get_mg_ctime_swaps(void)
> > > +{
> > > +	int i;
> > > +	long sum = 0;
> > > +	for_each_possible_cpu(i)
> > > +		sum += per_cpu(mg_ctime_swaps, i);
> > > +	return sum < 0 ? 0 : sum;
> > > +}
> > > +
> > >  long get_nr_dirty_inodes(void)
> > >  {
> > >  	/* not actually dirty inodes, but a wild approximation */
> > > @@ -2655,6 +2697,7 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  
> > >  			/* Get a fine-grained time */
> > >  			fine = ktime_get();
> > > +			this_cpu_inc(mg_fine_stamps);
> > >  
> > >  			/*
> > >  			 * If the cmpxchg works, we take the new
> > > floor value. If
> > > @@ -2663,11 +2706,14 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  			 * as good, so keep it.
> > >  			 */
> > >  			old = floor;
> > > -			if (!atomic64_try_cmpxchg(&ctime_floor,
> > > &old, fine))
> > > +			if (atomic64_try_cmpxchg(&ctime_floor,
> > > &old, fine))
> > > +				this_cpu_inc(mg_floor_swaps);
> > > +			else
> > >  				fine = old;
> > >  			now = ktime_mono_to_real(fine);
> > >  		}
> > >  	}
> > > +	this_cpu_inc(mg_ctime_updates);
> > >  	now_ts = timestamp_truncate(ktime_to_timespec64(now),
> > > inode);
> > >  	cur = cns;
> > >  
> > > @@ -2682,6 +2728,7 @@ struct timespec64
> > > inode_set_ctime_current(struct inode *inode)
> > >  		/* If swap occurred, then we're (mostly) done */
> > >  		inode->i_ctime_sec = now_ts.tv_sec;
> > >  		trace_ctime_ns_xchg(inode, cns, now_ts.tv_nsec,
> > > cur);
> > > +		this_cpu_inc(mg_ctime_swaps);
> > >  	} else {
> > >  		/*
> > >  		 * Was the change due to someone marking the old
> > > ctime QUERIED?
> > > @@ -2751,3 +2798,24 @@ umode_t mode_strip_sgid(struct mnt_idmap
> > > *idmap,
> > >  	return mode & ~S_ISGID;
> > >  }
> > >  EXPORT_SYMBOL(mode_strip_sgid);
> > > +
> > > +static int mgts_show(struct seq_file *s, void *p)
> > > +{
> > > +	long ctime_updates = get_mg_ctime_updates();
> > > +	long ctime_swaps = get_mg_ctime_swaps();
> > > +	long fine_stamps = get_mg_fine_stamps();
> > > +	long floor_swaps = get_mg_floor_swaps();
> > > +
> > > +	seq_printf(s, "%lu %lu %lu %lu\n",
> > > +		   ctime_updates, ctime_swaps, fine_stamps,
> > > floor_swaps);
> > > +	return 0;
> > > +}
> > > +
> > > +DEFINE_SHOW_ATTRIBUTE(mgts);
> > > +
> > > +static int __init mg_debugfs_init(void)
> > > +{
> > > +	debugfs_create_file("multigrain_timestamps", S_IFREG |
> > > S_IRUGO, NULL, NULL, &mgts_fops);
> > > +	return 0;
> > > +}
> > > +late_initcall(mg_debugfs_init);
> > > 
> > > -- 
> > > 2.45.2
> > > 
> > > 
> 
> -- 
> Jeff Layton <jlayton@kernel.org>
>

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.